Phi 4 Reasoning

Reasoning model by Microsoft.

Phi-4-reasoning is Microsoft's 14-billion parameter reasoning model specialized in step-by-step logical deduction, STEM proofs, and rigorous code verification.

Get API keyPlayground
Models / Phi 4 ReasoningID: azure_ai/Phi-4-reasoning

Maker

Microsoft

Served On: Azure Foundry

Specifications

Context window, ranked against other reasoning models

Insufficient data

No published context window for this model or its peers.

Context window

—

Max output

—

Modality

reasoning

Vision
Function calling
System prompt

Pricing

Rates are read live

Pricing for Phi-4-reasoning is fetched from the live catalogue on load, so it is never served from a cache that could outlive a repricing.

Availability

Not enough data yet

We have not collected enough health probes for this model to publish an uptime or latency figure. A percentage from a handful of samples is fabricated precision, so none is shown until the sample count supports one.

How Phi 4 Reasoning is billed

Billed at the provider's list price, with no per-token markup.

Exact list price
Tokens settle at the published rate of the model that served your call.
Cache discounts passed through
Provider prompt-caching discounts reach your balance with no added fee.
Cost on every response
Each response carries the x-nr-request-cost header, so you can reconcile spend per request.

More from Microsoft

Phi-4-multimodal-instructPhi-4Phi-4-mini-instructPhi-4-mini-reasoning

Start building with Phi-4-reasoning

One API key, three steps. Choose your tool to begin.

  1. Get a key

    Create API key

  2. Set your API key

    export NROUTER_API_KEY="<YOUR_API_KEY>"

  3. Configure Claude Code

    Choose a tool, then copy its setup from the panel.

npm install -g @anthropic-ai/claude-code
Claude Code · azure_ai/Phi-4-reasoning
# Point Claude Code to nRouter gateway
export ANTHROPIC_BASE_URL="https://api.nrouter.ai"
export ANTHROPIC_API_KEY="$NROUTER_API_KEY"

# Launch with azure_ai/Phi-4-reasoning
claude --model azure_ai/Phi-4-reasoning

Questions? Answers.

What is Phi 4 Reasoning?

Phi-4-reasoning is Microsoft's 14-billion parameter reasoning model specialized in step-by-step logical deduction, STEM proofs, and rigorous code verification.

How much does Phi 4 Reasoning cost?

Phi 4 Reasoning is billed at the provider's list price on nRouter with no per-token markup — tokens settle at the exact upstream rate. Input and output rates are read live, so see the pricing section above for the current figures.

Does Phi 4 Reasoning support tool calling and structured outputs?

Yes. Phi 4 Reasoning supports tool calling (function calling), so it can invoke external tools and APIs during a conversation.

What inputs and outputs does Phi 4 Reasoning support?

Phi 4 Reasoning takes text as input and returns text as output.

How do I use Phi 4 Reasoning via nRouter?

Use any OpenAI-compatible client: point it at https://api.nrouter.ai/v1 with your nRouter API key and set the model to "azure_ai/Phi-4-reasoning". The quick-start panel above has a copy-paste curl command for this model.

When was Phi 4 Reasoning released?

Phi 4 Reasoning was released on February 26, 2025.

Where is the Phi 4 Reasoning documentation?

Start at nrouter.ai/docs. The quick-start guide (nrouter.ai/docs/getting-started/quick-start) covers API keys and your first request, and the API reference (nrouter.ai/docs/api-reference) lists every parameter.

What other text models does Microsoft have?

Other Microsoft text models on nRouter include Phi-4 Multimodal Instruct (nrouter.ai/models/phi-4-multimodal-instruct), Phi 4 (nrouter.ai/models/phi-4), Phi 4 Mini Instruct (nrouter.ai/models/phi-4-mini-instruct), Phi 4 Mini Reasoning (nrouter.ai/models/phi-4-mini-reasoning).